Bounding box coordinates, width and height.

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I am using the deepstream-yolo-app on Tesla. I need the full yolo output per frame (bounding box coordinates, width and height) along with the classification label for all the detected objects in the frame. Can anyone please tell me how I may do that? Thanks in advance.

2

Hi,

You can find the whole tensor output here:
[url]https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps/blob/master/yolo/lib/yolov3.cpp#L31[/url]

Thanks.